Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases relating to risks and dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تز
    -0.15
     coup
    -0.15
    alah
    -0.15
    ERIC
    -0.14
    -transitional
    -0.14
    ventus
    -0.14
    ilen
    -0.14
    arent
    -0.14
    Ñıви
    -0.14
    EDIA
    -0.14
    POSITIVE LOGITS
    869
    0.17
     Campbell
    0.16
    0.15
     even
    0.14
    132
    0.14
     danger
    0.14
    940
    0.14
    anka
    0.14
     McM
    0.14
     lower
    0.13
    Act Density 0.068%

    No Known Activations